CheckedCare

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover readOnly, idempotent, non-destructive and closed-world, so the bar is low; the description still adds real value by disclosing the result cap (up to 10 matches), the fields returned (street, ZIP, license number) for disambiguating a match, and the record_key needed by the sibling tool. With no output schema, this return-shape disclosure is exactly what an agent otherwise could not infer.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with the trigger condition before the exclusions and the return description. Every clause carries routing or behavioral information; nothing is repeated from the schema or annotations.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a three-parameter read-only search with no output schema, the description covers the trigger, the exclusions, the result cardinality and returned fields, and the downstream handoff. An agent has everything needed to decide to call it and to interpret the response.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every parameter is already documented, and the description largely restates that the query may be a name, partial name, or license number and that city narrows results. It does hint that state must be a covered state, but adds no format, matching-behavior, or case-sensitivity detail beyond the schema. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (find), a specific resource (child care facility / licensing record), the identifying inputs (name, license number, name+city), and the scope limit (covered US states). It also explicitly separates itself from the sibling get_facility_record by naming the record_key handoff, so an agent can distinguish the two without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Opens with an explicit trigger ('Use this when the user names a child care center...'), then gives explicit exclusions: not for general child care advice, not for ranking/recommending, not for information about individuals. It also points forward to get_facility_record for the follow-up step, which is the only alternative an agent needs to route to.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only, idempotent, closed-world and non-destructive, so the description's added value is the return shape: verbatim findings, status-as-of date, official record link and CheckedCare page URL. The only real gap is the absence of any note on rate limits, caching or what happens when a slug doesn't match.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, all load-bearing: trigger and identifying inputs first, then the return contents, then the exclusion list. No restatement of the title or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only 3-parameter lookup with no output schema, the description supplies the output contents, the identification modes and the scope boundaries, which is everything an agent needs to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema describes all three parameters, so the schema does the heavy lifting. The description adds only that the slug originates from find_facility and that the license number may be user-supplied, which is useful disambiguation but limited beyond the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('get ... official record') and enumerates the payload (license status, inspection counts, agency findings), which distinguishes it clearly from the sibling find_facility, whose slug output is explicitly named as the input to this tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit trigger condition (one specific facility already identified via a record_key slug or a user-supplied license number) and explicit exclusions (no grading/ranking/comparison, no staff or child lookups), leaving little to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.